Tracking concepts and presenting content in a learning system

Abstract

A learning system capable of adaptively presenting various learning materials of various concepts to a user may include a concept tracker to analyze the learning materials and track one or more concepts from each of content items in the learning materials. A content item may be a video, and the system may analyze the transcripts of the video to determine one or more concepts about the video. The learning system may recommend a concept for the user to learn or improve based on the user's understanding and knowledge level around relevant concepts. Further, the system may present learning materials about the recommended concept to the user by indexing video segments by the time stamps associated with the particular concept and replay the video segments from the respective starting position and the ending position without replaying the entire video contents. Various clustering methods may be used to track the concepts.

What is claimed is: 
     
       1. A system for delivering content to a user, the system comprising:
 one or more processors; and 
 memory encoding instructions which, when executed by the one or more processors, cause the system to:
 access a content database including a plurality of content items and determine one or more concepts associated with each of the content items; 
 receive one or more user assessment variables based on a response by a user to a first content item of the content database; 
 generate a user model comprising a factor graph that includes variable nodes representing the one or more user assessment variables, wherein the user model predicts a knowledge level of the user; 
 recommend a concept of the one or more concepts based on the one or more user assessment variables and the predicted knowledge level; 
 display, to the user, one or more segments of the plurality of content items that are associated with the concept; and 
 display, while the one or more segments of the plurality of content items are displayed, a plot comprising one or more regions representing the concept over a timeline, the regions being separated by one or more time stamps associated with the concept, wherein the plot includes indications of a strength of the concept within the one or more regions over the timeline. 
 
 
     
     
       2. The system of  claim 1 , wherein at least a content item of the plurality of content items comprises transcripts of an audio/video media, and wherein the one or more concepts associated with the content item each include one or more time stamps, each of the time stamps comprising a starting position and an ending position of the audio/video media associated with at least a respective one of the one or more concepts. 
     
     
       3. The system of  claim 2 , wherein the instructions further cause the system to determine the one or more segments of the plurality of content items by:
 indexing the one or more segments of the plurality of content items based on the one or more time stamps associated with the concept; 
 determining starting and ending positions of each of the one or more segments based on a respective time stamp of the one or more time stamps; and 
 displaying the one or more segments of the plurality of content items that are associated with the concept by replaying the content item associated with the concept based on the starting and ending positions of each of the one or more segments. 
 
     
     
       4. The system of  claim 2 , wherein the instructions further cause the system to adjust the starting and/or ending positions of at least a segment of the one or more segments. 
     
     
       5. The system of  claim 2 , wherein the instructions further cause the system to adjust audio volume of at least a segment of the one or more segments near the starting and/or ending position of the segment. 
     
     
       6. The system of  claim 2 , wherein the instructions further cause the system to determine the one or more concepts associated with each content item by using a word embedding clustering method over transcripts of each content item. 
     
     
       7. A method for delivering content to a user, the method comprising:
 accessing a content database including a plurality of content items to determine one or more concepts associated with each of the content items; 
 receiving one or more user assessment variables based on a response by the user to a first content item of the content database; 
 predicting a knowledge level of the user based on the one or more user assessment variables and using a generated user model comprising a factor graph that includes variable nodes representing the one or more user assessment variables; 
 recommending a concept from the one or more concepts based on the one or more user assessment variables and the predicted knowledge level; 
 displaying one or more segments of the plurality of content items that are associated with the concept; and 
 displaying, while the one or more segments of the plurality of content items are displayed, a plot comprising one or more regions representing the concept over a timeline, the regions being separated by one or more time stamps associated with the concept, wherein the plot includes indications of a strength of the concept within the one or more regions over the timeline. 
 
     
     
       8. The method of  claim 7 , wherein at least a content item of the plurality of content items comprises transcripts of an audio/video media, and wherein the one or more concepts associated with the content item each includes one or more time stamps, each of the time stamps comprises a starting position and an ending position of the audio/video media. 
     
     
       9. The method of  claim 8  further comprising determining the one or more segments of the plurality of content items by:
 indexing the one or more segments of the plurality of content items based on the one or more time stamps associated with the concept; and 
 determining starting and ending positions of each of the one or more segments based on a respective timestamp; 
 wherein displaying the one or more segments of the plurality of content items that are associated with the concept comprises replaying the content item associated with the concept based on the starting and ending positions of each of the one or more segments. 
 
     
     
       10. The method of  claim 8  further comprising performing one or more of operations comprising:
 adjusting the starting and/or ending positions of at least a segment of the one or more segments; or 
 adjusting audio volume of at least a segment of the one or more segments near the starting and/or ending position of the segment. 
 
     
     
       11. The method of  claim 8 , wherein determining the one or more concepts associated with each of the content items comprises using a word embedding clustering method over transcripts of each content item. 
     
     
       12. A system for delivering content to a user, the system comprising:
 one or more processors; and 
 memory encoding instructions which, when executed by the one or more processors, cause the system to:
 access a content database including a plurality of content items and determine one or more concepts associated with each of the content items; 
 segment a content item of the content items into one or more segmented areas; 
 associate the one or more segmented areas of the content item with the one or more concepts associated with the content item; 
 recommend a concept of the one or more concepts based on at least one user assessment variable and a predicted knowledge level of the user, wherein the predicted knowledge level is generated using a user model comprising a factor graph that includes variable nodes representing the at least one user assessment variable; 
 display one or more of the segmented areas of the content item, the one or more segmented areas being associated with the concept; and 
 display, while the one or more of the segmented areas are displayed to the user, a plot comprising one or more regions representing the concept over a timeline, the regions being separated by one or more time stamps associated with the concept, wherein the plot includes indications of a strength of the concept within the one or more regions over the timeline. 
 
 
     
     
       13. The system of  claim 12 , wherein the instructions further cause the system to determine the one or more concepts associated with each of the content items by using a word embedding clustering method over transcripts of each of the content items.